论文标题
可解释的深度学习，以发现材料发现和设计的可行科学见解
Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design
论文作者
论文摘要
科学界对利用深度学习的力量越来越感兴趣，以解决各种领域的挑战。但是，尽管在建立预测模型方面具有有效性，但由于其不透明的性质，从深层神经网络中提取可行的知识时仍存在基本挑战。在这项工作中，我们提出了通过将特定于域特异性可行属性注入分析管道中可调的“旋钮”的技术来探索深度学习模型的行为。通过将域知识纳入生成建模框架中，我们不仅能够更好地了解这些黑盒模型的行为，而且还为科学家提供了可行的见解，这些见解可能会导致基本发现。
The scientific community has been increasingly interested in harnessing the power of deep learning to solve various domain challenges. However, despite the effectiveness in building predictive models, fundamental challenges exist in extracting actionable knowledge from deep neural networks due to their opaque nature. In this work, we propose techniques for exploring the behavior of deep learning models by injecting domain-specific actionable attributes as tunable "knobs" in the analysis pipeline. By incorporating the domain knowledge in a generative modeling framework, we are not only able to better understand the behavior of these black-box models, but also provide scientists with actionable insights that can potentially lead to fundamental discoveries.
